summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorAlexander Graf2012-04-25 14:29:57 +0200
committerAlexander Graf2012-05-06 16:19:09 +0200
commitaf415087d2bbbef3cc25cdf371bfb0460cf66b3b (patch)
treeb8b2ec53eb2607bccb8ecf66c1869a42f1dd2034
parentKVM: PPC: Book3S: PR: Optimize entry path (diff)
downloadkernel-qcow2-linux-af415087d2bbbef3cc25cdf371bfb0460cf66b3b.tar.gz
kernel-qcow2-linux-af415087d2bbbef3cc25cdf371bfb0460cf66b3b.tar.xz
kernel-qcow2-linux-af415087d2bbbef3cc25cdf371bfb0460cf66b3b.zip
KVM: PPC: Book3S: PR: No isync in slbie path
While messing around with the SLBs we're running in real mode. The entry to guest space goes through rfid, which is context synchronizing, so there's no need to manually synchronize anything through isync. With this patch and a simple priviledged SPR access loop guest, I get a speed bump from 2035607 to 2181301 exits per second. Signed-off-by: Alexander Graf <agraf@suse.de>
-rw-r--r--arch/powerpc/kvm/book3s_64_slb.S2
1 files changed, 0 insertions, 2 deletions
diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S
index f2e6e48ea463..56b983e7b738 100644
--- a/arch/powerpc/kvm/book3s_64_slb.S
+++ b/arch/powerpc/kvm/book3s_64_slb.S
@@ -90,8 +90,6 @@ slb_exit_skip_ ## num:
or r10, r10, r12
slbie r10
- isync
-
/* Fill SLB with our shadow */
lbz r12, SVCPU_SLB_MAX(r3)